BeatViz Workflow Credits: When You Pay and How to Estimate Costs

Workflow creates an AI music video in several stages. The credit estimate on the start page is not charged all at once when you select Generate Video. The first frames, videos, optional lip sync and character generation have different charging points.

When does Workflow charge credits?

User actionCredit behavior
Generate Video on the start screenChecks sufficient first-frame credit balance; no charge at this click
Confirm Storyline → generate first framesCharges per first-frame image, 3 (Standard) or 5 (Pro/Premium) credits each
Generate All Videos or single-scene video generationCharges the chosen model's video credits; Singing also includes automatic lip-sync credits
Regenerate one video clipCharges that clip's video credits again; Singing includes its lip-sync cost again
Regenerate a first/end-frame imageCharges another first-frame generation at the task's tier rate; first-frame regeneration is paid-only
Lip Sync button outside SingingCharges lip-sync credits for that completed clip
AI-create a character imageCharges 2 credits

When a submitted generation fails under the documented refund conditions, the associated charge is returned. A job that never starts because you have insufficient credits is not charged.

First-frame image costs

  • Standard → Nano Banana 2: 3 credits per scene.
  • Pro or Premium → Seedream 5 Pro: 5 credits per scene.

First frames are created after you confirm the storyline, rather than on the first Generate Video click.

Video credit rates by generation tier

ModeClip configurationVideo credits per clip
Standard Fast8 s, 720p35
Standard Fast8 s, 1080p45
Standard Quality8 s, 720p215
Standard Quality8 s, 1080p230
Pro5 s, 1080p60
Pro10 s, 1080p120
Premium 768p5 / 8 / 10 s90 / 144 / 180
Premium 2K5 / 8 / 10 s150 / 240 / 300

Additional lip sync costs 20 credits per second according to the applicable clip-duration billing tier. Standard Singing does not offer 1080p.

Example A: A 24-second Storytelling video, Standard Fast 720p

With Standard's 8-second clip duration, a 24-second song section has three scenes:

  • First frames: 3 × 3 = 9 credits.
  • Videos: 3 × 35 = 105 credits.
  • Total for first frames and videos: 114 credits, assuming no regeneration, AI-created character or optional lip sync.

The 9 first-frame credits are charged after storyline confirmation; the 105 video credits are charged when video generation begins.

Example B: The same 24 seconds in Singing, Standard Fast 720p

For three 8-second clips:

  • First frames: 9 credits.
  • Videos: 105 credits.
  • Automatic lip sync: 24 × 20 = 480 credits.
  • Illustrative total: 594 credits, assuming all three clips are processed for 8 seconds, no failures/retries and no additional assets.

The automatic lip-sync amount is included when you start the video-generation stage, not in a separate manual button charge.

Example C: A 24-second Pro video with 5-second clips

A 24-second selection requires five scene generations, including one short final segment:

  • First frames: 5 × 5 = 25 credits.
  • Videos: 5 × 60 = 300 credits.
  • Total before optional lip sync: 325 credits.

The final short segment is still charged as a full clip. This is why selecting a clip duration matters for budgeting.

How to estimate a different song length

  1. Divide the selected audio duration by the model's clip length and round up to the number of scenes.
  2. Multiply the scene count by the correct first-frame cost.
  3. Multiply the scene count by the correct video clip cost.
  4. Add lip sync if using Singing or manually synchronizing clips, using the durations charged by the interface.
  5. Add any additional character generation and regeneration attempts.

Always treat the in-product checkout estimate as authoritative if rates or product choices have changed since this guide was written.

FAQs

Do I pay for the whole song when I first click Generate Video?

No. That click checks first-frame balance. Image credits are charged after Storyline confirmation, and video credits when you start rendering.

Is Singing included in the base video clip cost?

No. Singing adds a lip-sync component, charged together with video generation in that Content Mode.

Are draft tasks billed repeatedly when I reopen them?

Reopening an existing task is not the same as requesting a new image or video generation. Additional charges depend on actions such as regenerating frames or clips.


Continue learning: ← Previous: Add Lip Sync · Next: Recover Drafts →

Open BeatViz Workflow

Try BeatViz Workflow

Upload a song, choose a Content Mode, and let Workflow plan scenes, first frames, and clips for you.

BeatViz Workflow Credits: AI Video Cost Calculator Guide